© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 27-TRANSCODER-HP
    7. 57418
    Prev
    Next
    INDEX
    Explanations

    source code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     smart
    -0.29
    ower
    -0.27
    翳
    -0.26
    icles
    -0.26
     power
    -0.25
    æĻºæħ§
    -0.24
    browser
    -0.24
    æĸ°çļĦä¸Ģ
    -0.24
     hardware
    -0.23
     Cop
    -0.23
    POSITIVE LOGITS
    éĶļ
    0.29
    Anchor
    0.28
    ress
    0.28
     Stations
    0.27
    ema
    0.27
    CHA
    0.26
     Anchor
    0.26
    allee
    0.26
     anch
    0.26
     anchor
    0.26
    Activations Density 0.002%

    No Known Activations